Search results

Sustainability has been receiving increasing attention in recent times, due to increasing pressures from consumers and stakeholders. Based on few selected indicators, we suggest a method for calculating and forecasting the degree of sustainability supply chain considering the case of the IKEA Group.

In order to predict the sustainability of IKEA’s supply chain, utilizing IWAY fulfillment scores, this research uses the concept and theory of grey prediction models and moving probability-based Markov models.

According to the findings of prediction, we observe that the level of supply chain sustainability is declining for the case in the forecast year 2022. The results are perceived as per the outcomes of the first-order, one-variable-based grey prediction model (GM (1, 1) model) and the grey moving probability state Markov model-based error correction.

Operationalizing sustainability, we consider the contribution a company’s supply chain toward the advancement of human rights, ethical labor practices, environmental improvement and anti-corruption principles into the account of supply-chain sustainability.

In order to understand the future trends in the supply chain sustainability performances of the firms and make corrective actions, managers may take a note on the results of prediction and they can subsequently work on the policy implications.

We build an advanced prediction model for forecasting the level of sustainability performances for a case firm using the indicator of human rights, ethical labor practices, environmental improvement and anti-corruption principles.

This study aims to enhance real estate price prediction accuracy using advanced machine learning models, minimizing biases and inconsistencies inherent in traditional appraisal methods. By leveraging support vector regression (SVR) and gradient boosting machine (GBM), this study provides a data-driven approach to property valuation, improving decision-making for buyers, sellers and policymakers. This study also seeks to bridge the gap in machine learning applications for emerging markets like Jordan. This study’s research’s broader goal is to offer a transparent, efficient and reliable tool for property valuation that improves market efficiency and reduces transaction uncertainty.

This study uses machine learning techniques – SVR and GBM – to predict real estate prices in Amman, Jordan. Data was collected from the Department of Lands and Survey, covering residential property sales from March 2023 to December 2023. The data set underwent preprocessing, including one-hot encoding for categorical variables and logarithmic normalization for skewed data. Hyperparameter tuning was performed using grid search, and an ensemble approach compared multiple algorithms. Performance was evaluated using root mean squared error (RMSE), mean absolute percentage error (MAPE) and MAE. The findings were implemented into a user-friendly “PRICE IT” application for real-world application.

The results demonstrate that SVR outperforms GBM in predicting real estate prices, achieving the lowest RMSE (0.31) and MAPE (25%). The most influential factors in price determination are property area, location and apartment type. The study highlights that machine learning models provide superior accuracy compared to traditional appraisal methods. The findings support the integration of data-driven valuation techniques in real estate markets, reducing reliance on subjective human judgment. A user-friendly application was developed to enable nontechnical users to estimate property prices, making the research practical and impactful.

This study contributes to the growing field of machine learning applications in real estate by demonstrating the effectiveness of SVR and GBM in an emerging market context. Unlike previous research, it focuses on Amman, Jordan, where limited studies have explored advanced machine-learning models for price prediction. The study offers a practical, user-friendly valuation tool that real estate stakeholders can widely adopt. This research enhances decision-making and market efficiency by providing a transparent and objective alternative to traditional appraisal methods.

Accurately predicting the installed capacity of wind energy is essential for energy strategic planning, given the growing need for environmental protection worldwide and the quick development of renewable energy. In order to provide an unprecedented high-precision scheme for wind energy installed capacity prediction and to further become the primary driving force in the process of energy planning and decision-making, this research focuses on overcoming the limitations of conventional prediction models and creatively proposes a multi-parameter collaborative optimization GM(1,1) power model. This will help the energy field advance in a more efficient and scientific direction.

The theoretical framework of the fundamental GM(1,1) power model is thoroughly examined in this study and serves as the basis for further optimizations. To unlock the potential of each parameter optimization, single-parameter optimization investigations of the model are conducted from the viewpoints of the fractional optimization, background value optimization and grey action optimization, respectively. Conversely, an inventive multi-parameter collaborative optimization power model is built. The model is given dynamic flexibility by adding time-varying parameters. The sine function and interpolation technique are used to further optimize the background value. The model’s meaning is enhanced by the inclusion of a power exponent. Furthermore, several parameters are cooperatively tuned with the aid of the sophisticated Firefly algorithm, giving the model stronger predictive powers. A multi-dimensional and multi-regional model comparison analysis is formed by selecting the wind energy installed capacity data of North America, Italy, Japan and South Korea for in-depth empirical analysis in order to confirm the model’s validity.

The findings show that the multi-parameter collaborative optimization model (Model 5) has an exceptional in-sample and out-of-sample prediction effect. The relative prediction error MAPEs are 0.41% and 0.31%. It has a clear advantage over the simple GM(1,1) power model and other single optimization models in applications in North America, South Korea, Japan, and Italy. Its seven variable parameters are the reason for this. These factors help create a very accurate prediction effect through joint optimization from multiple perspectives. It is noteworthy that Model 4’s nonlinear optimization of the grey action is impressive. It performs better than background value optimization and fractional-order optimization. Furthermore, according to the model’s prognosis, North America’s installed wind energy capacity is expected to develop linearly and reach 513.214 bn kilowatts in 2035. This gives the planning for energy development in this area a vital foundation.

The novel idea of the multi-parameter collaborative optimization GM(1,1) power model and its clever integration with the firefly method to accomplish parameter optimization constitute the fundamental value of this study. The substantial benefits of multi-parameter optimization in the stability of the prediction effect have been firmly validated by a thorough comparison with the basic and single-optimization models. Like a lighthouse, this novel model illuminates a more accurate path for wind energy installed capacity prediction and offers high-value reference bases for a variety of aspects, including government energy planning, enterprise strategic layout, investor decision-making direction, fostering technological innovation, advancing academic research and developing energy transformation strategies. As a result, it becomes a significant impetus for the growth of the energy sector.

• (1)

  This study proposes a new gray prediction model. Compared with the traditional grey prediction model, the modeling mechanism of this model is optimized.

• (2)

  This study is based on multi-parameter collaborative optimization to achieve the improvement of model prediction effect. The traditional grey model is two-parameter, while the model proposed in this study is seven-parameter collaborative optimization;

• (3)

  In this study, swarm intelligence algorithm-firefly algorithm is used to optimize the hyperparameters, so as to obtain the best cooperative optimization multi-parameter values;

• (4)

  The application of the model is divided into two parts: empirical and application. In the empirical stage, 5 kinds of prediction models are used to predict, which proves that the model proposed in this paper is effective and improves the prediction accuracy. The application part uses the model to forecast the installed wind power capacity in North America, and the future development trend is linear growth, which is expected to double the installed capacity by 2035.

This study proposes a new gray prediction model. Compared with the traditional grey prediction model, the modeling mechanism of this model is optimized.

This study is based on multi-parameter collaborative optimization to achieve the improvement of model prediction effect. The traditional grey model is two-parameter, while the model proposed in this study is seven-parameter collaborative optimization;

In this study, swarm intelligence algorithm-firefly algorithm is used to optimize the hyperparameters, so as to obtain the best cooperative optimization multi-parameter values;

The application of the model is divided into two parts: empirical and application. In the empirical stage, 5 kinds of prediction models are used to predict, which proves that the model proposed in this paper is effective and improves the prediction accuracy. The application part uses the model to forecast the installed wind power capacity in North America, and the future development trend is linear growth, which is expected to double the installed capacity by 2035.

Predicting surface settlement at mountain tunnel entrances during construction is increasingly crucial for risk analysis, as the accuracy of these predictions directly impacts collapse risk assessments and personnel safety.

This study introduces a novel approach using a particle swarm optimization (PSO)-optimized long short-term memory (LSTM) neural network for surface settlement prediction. The PSO algorithm optimizes key hyperparameters of the LSTM model, including the number of hidden layer neurons, the learning rate and L2 regularization, while the Adam optimizer refines LSTM iterations. Dropout is used in combination with adaptive L2 regularization parameters to avoid overfitting situations, and sensitivity analysis of the remaining variables ensures the identification of the optimal solution.

The model, based on monitoring data from the Aketepu No. 1 Tunnel’s left tunnel, establishes evaluation criteria incorporating error margins and root mean square error (RMSE). By examining the range of maximum (minimum) settlement rates for the cumulative settlement values, the study determined that the section is exposed to an average risk of collapse with slow deformation, which is consistent with actual observations.

This suggests that construction can proceed normally, with appropriate monitoring to mitigate the risk of collapse. The PSO-LSTM forecast model presents a promising approach for predicting collapse risks at mountain tunnel entrances.

This paper aims to enhance early-stage cost estimation in construction projects, a critical factor in project feasibility, funding, resource allocation and scheduling. Traditional cost estimation approaches suffer from limitations such as the absence of structured methodologies, assumptions of linear cost relationships, prolonged processes and expert judgment variations. To address these challenges, this study proposes a reliable cost prediction model based on artificial neural networks (ANNs) for building construction projects in India.

To develop cost prediction model, this study collected data from 377 building construction projects in India, encompassing 17 essential cost parameters. The methodology involves data preprocessing, constructing features and fine-tuning ANN hyperparameters meticulously to achieve optimal performance.

The research showcases effectiveness of cost prediction model, evident in significantly reduced mean square error values. ANN-based prediction model excels in handling nonlinear cost dependencies and diverse project complexities, making it a valuable tool for early-stage cost estimation.

ANN-based cost prediction model is primarily designed for predicting costs associated with structural works of building projects.

The proposed solution offers stakeholders a robust data-driven decision-making tool during initial phases of construction projects. This can lead to more successful and economically viable outcomes.

This research examines the drawbacks of traditional cost estimation methods by presenting a data-driven approach leveraging machine learning. It significantly improves precision of early cost forecasts in construction projects while offering practical value to industry.

The objective of this study is to accurately predict the cost of green buildings to provide quantifiable criteria for investment decisions from investors.

This study proposes a hybrid prediction model ML-based for cost prediction of GBPs and obtains prediction parameters (PPs) associated with project characteristics through data mining (DM) techniques. The model integrates a principal component analysis (PCA) method to perform parameter dimensionality reduction (PDR) on a large number of raw variables to provide independent characteristic terms. Moreover, the support vector machine (SVM) algorithm is improved to optimize the prediction results and integrated with parameter dimensionality reduction and cost prediction.

The prediction results show that the mean absolute and relative errors of the hybrid prediction model proposed in this study are equal to 39.78 and 0.02, respectively, which are much lower than those of the traditional SVM model and MRA prediction model. Moreover, the hybrid prediction model with parameter dimensionality reduction also achieved better prediction accuracy (R² = 0.319) and superior prediction accuracy for different cost terms.

Theoretically, the hybrid prediction model developed in this study can reliably predict the cost while accurately capturing the characteristics of GBPs, which is a bold attempt at a comprehensive approach. Practically, this study provides developers with a new ML-based prediction model that is capable of capturing the costs of projects with ambiguous definitions and complex characteristics.

The mobile communication industry in China is vulnerable to competition, industry regulation, macroeconomy and so on, which leads to service income's volatility and non-stationarity. Traditional income prediction models fail to take account of these factors, thus resulting in a low precision. The purpose of this paper is to to set up a new mobile communication service income prediction model based on grey system theory to overcome the inconformity between traditional models and qualitative analysis.

At first, mobile telecommunication service income is divided into number of users (NU) and average revenue per user (ARPU) prediction, respectively. Then, grey buffer operators are introduced to preprocess the time series according to their features and tendencies to eliminate the effect of shock disturbance. As a result, two grey models based on GM(1, 1) are constructed to forecast NU and ARPU, and thus the service income is obtained. At last, a case on Zhujiang mobile communication company is studied. The result proves that the proposed method is not only more accurate, but also could discover the turning point of income.

The results are convincing: it is more effective and accurate to employ grey buffer operator theory to predict the mobile communication service income compared with other methods. Besides, this method is applicable to cases with less data samples and faster development.

It's common to come across a system with less data and poor information. At this case, the grey prediction method exposed in the paper can be used to forecast the future trend which will give the predictors advice to achieve fine outcomes. Buffer operators can reduce the effect of shock disturbance and the GM(1, 1) model has the advantages of exploiting information using only a couple of data.

Considering the fast development of China's mobile communication in recent years, only limited data can be acquired to predict the future, which will definitely reduce the prediction precision using traditional models. The paper succeeds in introducing GM(1, 1) model based on grey buffer operators into the income prediction and the outcome proves that it has higher prediction precision and extensive application.

The purpose of this paper is to discuss the interval forecasting, prediction interval and its reliability. When the predicted interval and its reliability are construction, the general rule which must satisfy is studied, grey wrapping band forecasting method is perfect.

A forecasting method puts forward a process of prediction interval. It also elaborates on the meaning of interval (the probability of the prediction interval including the real value of predicted variable). The general rule is abstracted and summarized by many forecasting cases. The general rule is discussed by axiomatic method.

The prediction interval is categorized into three types. Three axioms that construction predicted interval must satisfy are put forward. Grey wrapping band forecasting method is improved based on the proposed axioms.

Take the Shanghai composite index as the example, according to the K-line diagram from 4 January 2013 to 9 May 2013, the reliability of predicted rebound height of subsequent two or three trading day does not exceed the upper wrapping curve is 80 per cent. It is significant to understand the forecasting range correctly, build a reasonable range forecasting method and to apply grey wrapping band forecasting method correctly.

Grey wrapping band forecasting method is improved based on the proposed axioms.

Effectively predicting research and development project portfolio benefit (R&D PPB) could assist organizations in monitoring the execution of research and development project portfolio (R&D PP). However, due to the uncertainty and complexity of R&D PPB, current research remains lacking a valid R&D PPB prediction tool. Therefore, an R&D PPB prediction model is proposed via a backpropagation neural network (BPNN).

The R&D PPB prediction model is constructed via a refined immune genetic algorithm coupling backpropagation neural network (RIGA-BPNN). Firstly, considering the characteristics of R&D PP, benefit evaluation criteria are identified. Secondly, the benefit criteria values are derived as input variables to the model via trapezoidal fuzzy numbers, and then the R&D PPB value is determined as the output variable through the CRITIC method. Thirdly, a refined immune genetic algorithm (RIGA) is designed to optimize BPNN by enhancing polyfitness, crossover and mutation probabilities. Lastly, the R&D PPB prediction model is constructed via the RIGA-BPNN, followed by training and testing.

The accuracy of the R&D PPB prediction model stands at 99.26%. In addition, the comparative experiment results indicate that the proposed model surpasses BPNN and the immune genetic algorithm coupling backpropagation neural network (IGA-BPNN) in both convergence speed and accuracy, showcasing superior performance in R&D PPB prediction. This study enriches the R&D PPB predicting methodology by providing managers with an effective benefits management tool.

The research implications of this study encompass three aspects. First, this study provides a profound insight into R&D PPB prediction and enriches the research in PP fields. Secondly, during the construction of the R&D PPB prediction model, the utilization of the composite system synergy model for quantifying synergy contributes to a comprehensive understanding of intricate interactions among benefits. Lastly, in this research, a RIGA is proposed for optimizing the BPNN to efficiently predict R&D PPB.

This study carries threefold implications for the practice of R&D PPM. To begin with, the approach proposed serves as an effective tool for managers to predict R&D PPB. Then, the model excels in efficiency and flexibility. Furthermore, the proposed model could be used to tackle additional challenges in R&D PPM, such as gauging the potential risk level of R&D PP.

Effective predicting of R&D PPB enables organizations to allocate their limited resources more strategically, ensuring optimal use of capital, manpower and time. By accurately predicting benefit, an organization can prioritize high-potential initiatives, thereby improving innovation efficiency and reducing the risk of failed investments. This approach not only strengthens market competitiveness but also positions organizations to adapt more effectively to changing market conditions, fostering long-term growth and sustainability in a competitive business environment.

Incorporating the characteristics of R&D PP and quantifying the synergy between benefits, this study facilitates a more insightful R&D PPB prediction. Additionally, improvements to the polyfitness, crossover and mutation probabilities of IGA are made, and the aforementioned RIGA is applied to optimize the BPNN. It significantly enhances the prediction accuracy and convergence speed of the neural network, improving the effectiveness of the R&D PPB prediction model.

This paper aims to reduce the impact of noise on the prediction accuracy of remaining useful life (RUL) for supercapacitor. First, Savitzky–Golay (SG) smoothing filter method (Savitzky and Golay, 1964) is used to eliminate the local small fluctuation and high-frequency noises that are generated by the capacity drop and rebound during the charging and discharging process of supercapacitor. Then, the variational mode decomposition (VMD) method is used to eliminate large fluctuation noises that are caused by internal temperature change of supercapacitor and chemical reaction of the supercapacitor. Its parameters are optimized by using marine predators algorithm (MPA), and the capacity sequence after denoising is reconstructed. Finally, long short term memory neural networks (LSTM) is used to predict the performance degradation law (PDL) and remaining useful life (RUL) of supercapacitor for the reconstructed sequence, then the comparative analysis is conducted with other methods, which results show this method improves the prediction accuracy effectively, and provides theoretical support for timely and accurately understanding the PDL and RUL of supercapacitor backup power supply.

First, SG smoothing filter method is used to eliminate the local small fluctuation and high-frequency noises that are generated by the capacity drop and rebound during the charging and discharging process of supercapacitor. Then, the VMD method is used to eliminate large fluctuation noises that are caused by internal temperature change of supercapacitor and chemical reaction of the supercapacitor. Its parameters are optimized by using MPA, and the capacity sequence after denoising is reconstructed. Finally, LSTM is used to predict the PDL and RUL of supercapacitor for the reconstructed sequence, then the comparative analysis is conducted with other methods, the results show that this method improves the prediction accuracy effectively, and provides theoretical support for timely and accurate understanding the PDL and RUL of supercapacitor backup power supply.

These factors will bring different types of noise during the service process of supercapacitor backup power supply, such as capacity regeneration, differences of charging and discharging rate, internal temperature change of supercapacitor, chemical reaction and external electromagnetic interference. Therefore, the paper proposes an LSTM prediction method of supercapacitor’s PDL and RUL based on composite denoising, which is divided into three stages: smoothing, noise reduction and prediction. First, SG smoothing filter method is used to eliminate the local small fluctuation and high-frequency noises, and MPA-VMD method is used to eliminate the nonlinear and nonstationary noises. Then, the capacity sequence after denoising is reconstructed, LSTM is used to predict PDL and RUL of supercapacitor. Finally, the comparative analysis with other methods is carried out. The results show that SG-VMD-LSTM method has higher prediction accuracy, which can accurately predict PDL and RUL of supercapacitor backup power supply, and improve the safety and reliability of wind turbine operation under the severe wind conditions.

The comparative analysis with other methods is carried out. The results show that SG-VMD-LSTM method has higher prediction accuracy, which can accurately predict PDL and RUL of supercapacitor backup power supply, and improve the safety and reliability of wind turbine operation under the severe wind conditions.